Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code/software development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PACKET
    -0.07
    (preg
    -0.07
     DOMAIN
    -0.07
    orsch
    -0.07
     EST
    -0.07
    携带
    -0.06
     Lester
    -0.06
     ô
    -0.06
     ancient
    -0.06
     מכ
    -0.06
    POSITIVE LOGITS
     klientów
    0.07
    whel
    0.07
    Toolbar
    0.07
     marijuana
    0.07
    -Shirt
    0.07
     blows
    0.07
    .'"
    0.07
    Pedido
    0.07
     Datos
    0.07
     adım
    0.07
    Act Density 0.008%

    No Known Activations